Title :
Intelligent classification of fetal Doppler blood velocity waveform abnormalities using wavelet transform and vector quantization algorithm
Author :
Izzetoglu, Kurtulus ; Erkmen, Aydan M. ; Beksac, Sinan
Author_Institution :
Dept. of Electr. & Electron. Eng., Middle East Tech. Univ., Ankara, Turkey
Abstract :
The approach presented in this paper uses the features, represented by wavelet coefficients, that are extracted from the variations of blood velocity waveforms obtained from Doppler ultrasound images of fetal umbilical arteries. The obtained reliable features form the training samples of a classification algorithm to be used in intelligent diagnostic for fetal surveillance
Keywords :
Doppler effect; biomedical ultrasonics; diagnostic expert systems; feature extraction; image classification; neural nets; vector quantisation; wavelet transforms; Doppler ultrasound images; blood velocity waveforms; feature extraction; fetal umbilical arteries; intelligent classification; intelligent diagnostics; unsupervised neural network; vector quantisation; wavelet coefficients; Arteries; Artificial neural networks; Biomedical engineering; Blood flow; Data mining; Feature extraction; Frequency; Surveillance; Ultrasonic imaging; Wavelet coefficients;
Conference_Titel :
Systems, Man and Cybernetics, 1995. Intelligent Systems for the 21st Century., IEEE International Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-2559-1
DOI :
10.1109/ICSMC.1995.537850
